Unverified Commit 6fbebb4b authored by Angelika Romanou's avatar Angelika Romanou Committed by GitHub
Browse files

Add INCLUDE tasks (#2769)



* Add INCLUDE tasks

* pacify pre-commit

---------
Co-authored-by: default avatarBaber <baber@hey.com>
parent bb4fa95e
from functools import partial
CATEGORIES = [
"Applied Science",
"Arts & Humanities",
"Business & Commerce",
"Driving License",
"General knowledge",
"Health oriented education",
"Marine License",
"Medical License",
"Professional certification",
"STEM",
"Social Science",
]
def process_docs(dataset, category):
return dataset.filter(lambda x: x["domain"] == category)
process_functions = {
f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
process_docs, category=category
)
for category in CATEGORIES
}
globals().update(process_functions)
group: include_base_44_kazakh
task:
- include_base_44_kazakh_few_shot_en_arts_humanities
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
dataset_path: CohereForAI/include-base-44
dataset_name: Kazakh
test_split: test
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
D. {{option_d}}\nAnswer:"
doc_to_choice:
- A
- B
- C
- D
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
metadata:
version: 0.0
include: _kazakh_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Arts
& Humanities.
process_docs: !function 'utils.process_arts_humanities'
task: include_base_44_kazakh_few_shot_en_arts_humanities
from functools import partial
CATEGORIES = [
"Applied Science",
"Arts & Humanities",
"Business & Commerce",
"Driving License",
"General knowledge",
"Health oriented education",
"Marine License",
"Medical License",
"Professional certification",
"STEM",
"Social Science",
]
def process_docs(dataset, category):
return dataset.filter(lambda x: x["domain"] == category)
process_functions = {
f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
process_docs, category=category
)
for category in CATEGORIES
}
globals().update(process_functions)
group: include_base_44_korean
task:
- include_base_44_korean_few_shot_en_professional_certification
- include_base_44_korean_few_shot_en_social_science
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
dataset_path: CohereForAI/include-base-44
dataset_name: Korean
test_split: test
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
D. {{option_d}}\nAnswer:"
doc_to_choice:
- A
- B
- C
- D
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
metadata:
version: 0.0
include: _korean_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Professional
certification.
process_docs: !function 'utils.process_professional_certification'
task: include_base_44_korean_few_shot_en_professional_certification
include: _korean_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Social
Science.
process_docs: !function 'utils.process_social_science'
task: include_base_44_korean_few_shot_en_social_science
from functools import partial
CATEGORIES = [
"Applied Science",
"Arts & Humanities",
"Business & Commerce",
"Driving License",
"General knowledge",
"Health oriented education",
"Marine License",
"Medical License",
"Professional certification",
"STEM",
"Social Science",
]
def process_docs(dataset, category):
return dataset.filter(lambda x: x["domain"] == category)
process_functions = {
f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
process_docs, category=category
)
for category in CATEGORIES
}
globals().update(process_functions)
group: include_base_44_lithuanian
task:
- include_base_44_lithuanian_few_shot_en_arts_humanities
- include_base_44_lithuanian_few_shot_en_stem
- include_base_44_lithuanian_few_shot_en_social_science
- include_base_44_lithuanian_few_shot_en_business_commerce
- include_base_44_lithuanian_few_shot_en_professional_certification
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
dataset_path: CohereForAI/include-base-44
dataset_name: Lithuanian
test_split: test
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
D. {{option_d}}\nAnswer:"
doc_to_choice:
- A
- B
- C
- D
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
metadata:
version: 0.0
include: _lithuanian_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Arts
& Humanities.
process_docs: !function 'utils.process_arts_humanities'
task: include_base_44_lithuanian_few_shot_en_arts_humanities
include: _lithuanian_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Business
& Commerce.
process_docs: !function 'utils.process_business_commerce'
task: include_base_44_lithuanian_few_shot_en_business_commerce
include: _lithuanian_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Professional
certification.
process_docs: !function 'utils.process_professional_certification'
task: include_base_44_lithuanian_few_shot_en_professional_certification
include: _lithuanian_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about Social
Science.
process_docs: !function 'utils.process_social_science'
task: include_base_44_lithuanian_few_shot_en_social_science
include: _lithuanian_few_shot_en_template_yaml
description: The following are multiple-choice questions (with answers) about STEM.
process_docs: !function 'utils.process_stem'
task: include_base_44_lithuanian_few_shot_en_stem
from functools import partial
CATEGORIES = [
"Applied Science",
"Arts & Humanities",
"Business & Commerce",
"Driving License",
"General knowledge",
"Health oriented education",
"Marine License",
"Medical License",
"Professional certification",
"STEM",
"Social Science",
]
def process_docs(dataset, category):
return dataset.filter(lambda x: x["domain"] == category)
process_functions = {
f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
process_docs, category=category
)
for category in CATEGORIES
}
globals().update(process_functions)
group: include_base_44_malay
task:
- include_base_44_malay_few_shot_en_social_science
- include_base_44_malay_few_shot_en_business_commerce
- include_base_44_malay_few_shot_en_arts_humanities
aggregate_metric_list:
- metric: acc
weight_by_size: true
metadata:
version: 0.0
dataset_path: CohereForAI/include-base-44
dataset_name: Malay
test_split: test
output_type: multiple_choice
doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
D. {{option_d}}\nAnswer:"
doc_to_choice:
- A
- B
- C
- D
doc_to_target: answer
metric_list:
- metric: acc
aggregation: mean
higher_is_better: true
metadata:
version: 0.0
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment